Classification of heart sound short records using bispectrum analysis approach images and deep learning
- PDF / 4,057,231 Bytes
- 16 Pages / 595.276 x 790.866 pts Page_size
- 16 Downloads / 373 Views
(2020) 9:66
ORIGINAL ARTICLE
Classification of heart sound short records using bispectrum analysis approach images and deep learning Ali Mohammad Alqudah1 · Hiam Alquran1 · Isam Abu Qasmieh1 Received: 17 April 2020 / Revised: 11 August 2020 / Accepted: 31 August 2020 © Springer-Verlag GmbH Austria, part of Springer Nature 2020
Abstract The diagnosis of cardiac disorders using heart sounds is one of the hottest topics in recent years. In general, diagnosing in the early stage is usually performed using routine auscultation examination using a stethoscope which requires human interpretation. Recording of heart sounds using an electronic microphone embedded inside the stethoscope provides a digital recording which is known as a phonocardiogram (PCG). This PCG signal carries very informative data about the status of the heart and its valves. Recently, several machines and deep learning techniques employed signal processing to classify heart disorders using PCG. Based on the used datasets, heart sound can be exploited to classify five types of heart sounds, one is normal, and the others are abnormal and two classes of heart sound, normal and abnormal. This research used a modified version of previously proposed convolutional neural network (CNN) which is AOCTNet architecture for automatic diagnosis of heart valves conditions based on higher order spectral estimation using bispectrum of heart sounds recordings. The results show that the proposed system has a comparable performance comparing to other methods. The methodology proposed in this paper can detect heart valves disorders using PCG signals with an overall accuracy of 98.70 and 97.10% using full bispectrum images and contour bispectrum images, respectively, for five classes dataset and overall accuracy of 99.47 and 98.74% using full bispectrum images and contour bispectrum images, respectively, for two classes dataset. Keywords PCG · Classification · Bispectrum · Deep learning · Convolutional neural network
1 Introduction Heart and its valves are a permanent source of information/ data that reflects the status of the cardiovascular system and can be used to diagnose the heart diseases effectively (Karar et al. 2017). Data from Electrocardiogram (ECG) and phonocardiogram (PCG) are used to extract features that can be fed to artificial intelligence algorithms to classify diseases (Chaudhuri and Jayanthi 2016; Alqudah and Alqudah 2019). The most important issue in cardiovascular disease detection and classification is that it must be identified without delay (Khadra et al. 2005). Recording heart sounds is easier than acquiring its electrical activity, and it requires fewer connections than the second method; therefore, the researchers focus their * Ali Mohammad Alqudah [email protected] 1
Department of Biomedical Systems and Informatics Engineering, Hijjawi Faculty for Engineering Technology, Yarmouk University, Irbid 21163, Jordan
attention on using it for further information on the heart health diagnosis. (Chaudhuri and Jayanthi 2016; Karar et al. 2
Data Loading...
